October 24, 2026· ~3 min readArchitecting Governed, Self-Evolving AI Agents on Google Cloud # Architecting Governed, Self-Evolving AI Agents on Google Cloud How far can you push "self-evolving" agents when governance is the actual requireme
October 24, 2026· ~3 min readEvaluating AI agents: moving past the vibe check # Evaluating AI agents: moving past the vibe check Agent evaluation defaults to intuition — "it feels better now." This post lays out the discipline
October 24, 2026· ~3 min readOptimizing a 200,000-line Python codebase overnight with Gemini 4 Argon # Optimizing a 200,000-line Python codebase overnight with Gemini 4 Argon An agentic overnight drive to optimize the Google Agent Development Kit (A
October 24, 2026· ~3 min readStep by Step guide: Build a Voice Agent That Never Goes Silent using ADK # Build a Voice Agent That Never Goes Silent using ADK A voice agent that leaves dead air while it works feels broken. This ADK guide shows two patt
October 11, 2026· ~2 min readAgent Anomaly Detection, now in Private Preview on the Gemini Enterprise Agent Platform # Agent Anomaly Detection, now in Private Preview Agent Anomaly Detection is a **reasoning-based oversight and audit layer** for autonomous agents d
October 11, 2026· ~2 min readAutonomous LLM post-training with Tunix on TPUs # Autonomous LLM post-training with Tunix on TPUs LLM post-training is a repetitive, mostly mechanical discipline: run a training job, watch loss cu